With the rapid development of deep learning-based detection algorithms,deep learning is widely used in the field of infrared small target detection.However,well-designed adversarial samples can fool human visual perce...With the rapid development of deep learning-based detection algorithms,deep learning is widely used in the field of infrared small target detection.However,well-designed adversarial samples can fool human visual perception,directly causing a serious decline in the detection quality of the recognition model.In this paper,an adversarial defense technology for small infrared targets is proposed to improve model robustness.The adversarial samples with strong migration can not only improve the generalization of defense technology,but also save the training cost.Therefore,this study adopts the concept of maximizing multidimensional feature distortion,applying noise to clean samples to serve as subsequent training samples.On this basis,this study proposes an inverse perturbation elimination method based on Generative Adversarial Networks(GAN)to realize the adversarial defense,and design the generator and discriminator for infrared small targets,aiming to make both of them compete with each other to continuously improve the performance of the model,find out the commonalities and differences between the adversarial samples and the original samples.Through experimental verification,our defense algorithm is not only able to cope with multiple attacks but also performs well on different recognition models compared to commonly used defense algorithms,making it a plug-and-play efficient adversarial defense technique.展开更多
Human Activity Recognition(HAR)has become a subject of concern and plays an important role in daily life.HAR uses sensor devices to collect user behavior data,obtain human activity information and identify them.Markov...Human Activity Recognition(HAR)has become a subject of concern and plays an important role in daily life.HAR uses sensor devices to collect user behavior data,obtain human activity information and identify them.Markov Logic Networks(MLN)are widely used in HAR as an effective combination of knowledge and data.MLN can solve the problems of complexity and uncertainty,and has good knowledge expression ability.However,MLN structure learning is relatively weak and requires a lot of computing and storage resources.Essentially,the MLN structure is derived from sensor data in the current scene.Assuming that the sensor data can be effectively sliced and the sliced data can be converted into semantic rules,MLN structure can be obtained.To this end,we propose a rulebase building scheme based on probabilistic latent semantic analysis to provide a semantic rulebase for MLN learning.Such a rulebase can reduce the time required for MLN structure learning.We apply the rulebase building scheme to single-person indoor activity recognition and prove that the scheme can effectively reduce the MLN learning time.In addition,we evaluate the parameters of the rulebase building scheme to check its stability.展开更多
基金supported in part by the National Natural Science Foundation of China under Grant 62073164the Shanghai Aerospace Science and Technology Innovation Foundation under Grant SAST2022-013.
文摘With the rapid development of deep learning-based detection algorithms,deep learning is widely used in the field of infrared small target detection.However,well-designed adversarial samples can fool human visual perception,directly causing a serious decline in the detection quality of the recognition model.In this paper,an adversarial defense technology for small infrared targets is proposed to improve model robustness.The adversarial samples with strong migration can not only improve the generalization of defense technology,but also save the training cost.Therefore,this study adopts the concept of maximizing multidimensional feature distortion,applying noise to clean samples to serve as subsequent training samples.On this basis,this study proposes an inverse perturbation elimination method based on Generative Adversarial Networks(GAN)to realize the adversarial defense,and design the generator and discriminator for infrared small targets,aiming to make both of them compete with each other to continuously improve the performance of the model,find out the commonalities and differences between the adversarial samples and the original samples.Through experimental verification,our defense algorithm is not only able to cope with multiple attacks but also performs well on different recognition models compared to commonly used defense algorithms,making it a plug-and-play efficient adversarial defense technique.
基金supported by the National Natural Science Foundation of China(No.61872038).
文摘Human Activity Recognition(HAR)has become a subject of concern and plays an important role in daily life.HAR uses sensor devices to collect user behavior data,obtain human activity information and identify them.Markov Logic Networks(MLN)are widely used in HAR as an effective combination of knowledge and data.MLN can solve the problems of complexity and uncertainty,and has good knowledge expression ability.However,MLN structure learning is relatively weak and requires a lot of computing and storage resources.Essentially,the MLN structure is derived from sensor data in the current scene.Assuming that the sensor data can be effectively sliced and the sliced data can be converted into semantic rules,MLN structure can be obtained.To this end,we propose a rulebase building scheme based on probabilistic latent semantic analysis to provide a semantic rulebase for MLN learning.Such a rulebase can reduce the time required for MLN structure learning.We apply the rulebase building scheme to single-person indoor activity recognition and prove that the scheme can effectively reduce the MLN learning time.In addition,we evaluate the parameters of the rulebase building scheme to check its stability.
